{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T11:02:00Z","timestamp":1778497320083,"version":"3.51.4"},"reference-count":32,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2022,9,27]],"date-time":"2022-09-27T00:00:00Z","timestamp":1664236800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In the recent past, hyper-spectral imaging has found widespread application in forensic science, performing both geometric characterization of biological traces and trace classification by exploiting their spectral emission. Methods proposed in the literature for blood stain analysis have been shown to be effectively limited to collaborative surfaces. This proves to be restrictive in real-case scenarios. The problem of the substrate material and color is then still an open issue for blood stain analysis. This paper presents a novel method for blood spectra correction when contaminated by the influence of the substrate, exploiting a neural network-based approach. Blood stains hyper-spectral images deposited on 12 different substrates for 12 days at regular intervals were acquired via a hyper-spectral camera. The data collected were used to train and test the developed neural network model. Starting from the spectra of a blood stain deposited in a generic substrate, the algorithm at first recognizes whether it is blood or not, then allows to obtain the spectra that the same blood stain, at the same time, would have on a reference white substrate with a mean absolute percentage error of 1.11%. Uncertainty analysis has also been performed by comparing the ground truth reflectance spectra with the predicted ones by the neural model.<\/jats:p>","DOI":"10.3390\/s22197311","type":"journal-article","created":{"date-parts":[[2022,9,28]],"date-time":"2022-09-28T03:30:37Z","timestamp":1664335837000},"page":"7311","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["Correction of Substrate Spectral Distortion in Hyper-Spectral Imaging by Neural Network for Blood Stain Characterization"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9922-3201","authenticated-orcid":false,"given":"Nicola","family":"Giulietti","sequence":"first","affiliation":[{"name":"Department of Mechanical Engineering, Politecnico di Milano, 20156 Milano, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Silvia","family":"Discepolo","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Mathematical Science, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2564-856X","authenticated-orcid":false,"given":"Paolo","family":"Castellini","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Mathematical Science, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Milena","family":"Martarelli","sequence":"additional","affiliation":[{"name":"Department of Industrial Engineering and Mathematical Science, Universit\u00e0 Politecnica delle Marche, 60131 Ancona, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2022,9,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"010901","DOI":"10.1117\/1.JBO.19.1.010901","article-title":"Medical hyperspectral imaging: A review","volume":"19","author":"Lu","year":"2014","journal-title":"J. Biomed. Opt."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100368","DOI":"10.1016\/j.forc.2021.100368","article-title":"Occult bloodstains detection in crime scene analysis","volume":"26","author":"Legaz","year":"2021","journal-title":"Forensic Chem."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1024","DOI":"10.1111\/1556-4029.14643","article-title":"Degrees of contrast: Detection of latent bloodstains on fabric using an alternate light source (ALS) and the effects of washing","volume":"66","author":"James","year":"2020","journal-title":"J. Forensic Sci."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"312","DOI":"10.1007\/s00339-018-1739-6","article-title":"Hyperspectral imaging and multivariate analysis in the dried blood spots investigations","volume":"124","author":"Majda","year":"2018","journal-title":"Appl. Phys. A"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/j.forsciint.2012.09.012","article-title":"Hyperspectral imaging for non-contact analysis of forensic traces","volume":"223","author":"Edelman","year":"2012","journal-title":"Forensic Sci. Int."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1016\/j.forsciint.2012.03.009","article-title":"Identification and age estimation of blood stains on colored backgrounds by near infrared spectroscopy","volume":"220","author":"Edelman","year":"2012","journal-title":"Forensic Sci. Int."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Zulfiqar, M., Ahmad, M., Sohaib, A., Mazzara, M., and Distefano, S. (2021). Hyperspectral Imaging for Bloodstain Identification. Sensors, 21.","DOI":"10.3390\/s21093045"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Ksi\u0105\u017cek, K., Romaszewski, M., G\u0142omb, P., Grabowski, B., and Cholewa, M. (2020). Blood Stain Classification with Hyperspectral Imaging and Deep Neural Networks. Sensors, 20.","DOI":"10.3390\/s20226666"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Pa\u0142ka, F., Ksi\u0105\u017cek, W., P\u0142awiak, P., Romaszewski, M., and Ksi\u0105\u017cek, K. (2021). Hyperspectral Classification of Blood-Like Substances Using Machine Learning Methods Combined with Genetic Algorithms in Transductive and Inductive Scenarios. Sensors, 21.","DOI":"10.3390\/s21072293"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Velez-Reyes, M., and Messinger, D.W. (2016). Spectral feature characterization methods for blood stain detection in crime scene backgrounds. Proceedings SPIE 9840, Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XXII, SPIE.","DOI":"10.1117\/12.2224099"},{"key":"ref_11","first-page":"117","article-title":"Hyperspectral Imaging System Modeling","volume":"14","author":"Kerekes","year":"2003","journal-title":"Linc. Lab. J."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"110701","DOI":"10.1016\/j.forsciint.2021.110701","article-title":"A dataset for evaluating blood detection in hyperspectral images","volume":"320","author":"Romaszewski","year":"2021","journal-title":"Forensic Sci. Int."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"166","DOI":"10.1016\/j.forsciint.2010.07.034","article-title":"Age estimation of blood stains by hemoglobin derivative determination using reflectance spectroscopy","volume":"206","author":"Bremmer","year":"2011","journal-title":"Forensic Sci. Int."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.forsciint.2017.05.023","article-title":"Towards substrate-independent age estimation of blood stains based on dimensionality reduction and k-nearest neighbor classification of absorbance spectroscopic data","volume":"278","author":"Bergmann","year":"2017","journal-title":"Forensic Sci. Int."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.cis.2016.01.008","article-title":"Blood drop patterns: Formation and applications","volume":"231","author":"Chen","year":"2016","journal-title":"Adv. Colloid Interface Sci."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1016\/j.forsciint.2013.04.033","article-title":"Circumventing substrate interference in the Raman spectroscopic identification of blood stains","volume":"231","author":"McLaughlin","year":"2013","journal-title":"Forensic Sci. Int."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"107947","DOI":"10.1016\/j.apacoust.2021.107947","article-title":"A neural network based microphone array approach to grid-less noise source localization","volume":"177","author":"Castellini","year":"2021","journal-title":"Appl. Acoust."},{"key":"ref_18","unstructured":"Trevor, H., Robert, T., and Jerome, F. (2009). The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Springer."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Rosenblatt, F. (1961). Principles of Neurodynamics: Perceptrons and the Theory of Brain Mechanisms. Spartan Books.","DOI":"10.21236\/AD0256582"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., and McClelland, J.L. (1986). Learning internal representations by error propagation. Parallel Distributed Processing: Explorations in the Microstructure of Cognition: Foundations, MIT Press. Chapter 8.","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"3668","DOI":"10.1109\/TCYB.2019.2950779","article-title":"A survey of optimization methods from a machine learning perspective","volume":"50","author":"Sun","year":"2019","journal-title":"IEEE Trans. Cybern."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1515\/jib-2012-201","article-title":"On the parameter optimization of Support Vector Machines for binary classification","volume":"9","author":"Gaspar","year":"2012","journal-title":"J. Integr. Bioinform."},{"key":"ref_23","first-page":"3","article-title":"Bayesian Optimization is Superior to Random Search for Machine Learning Hyperparameter Tuning: Analysis of the Black-Box Optimization Challenge 2020","volume":"133","author":"Turner","year":"2021","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"106247","DOI":"10.1016\/j.knosys.2020.106247","article-title":"Fast Hyperparameter Tuning using Bayesian Optimization with Directional Derivatives","volume":"205","author":"Joy","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Nguyen, V. (2019, January 3\u20135). Bayesian Optimization for Accelerating Hyper-Parameter Tuning. Proceedings of the 2019 IEEE Second International Conference on Artificial Intelligence and Knowledge Engineering (AIKE), Sardinia, Italy.","DOI":"10.1109\/AIKE.2019.00060"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Joy, T.T., Rana, S., Gupta, S., and Venkatesh, S. (2016, January 4\u20138). Hyperparameter tuning for big data using Bayesian optimisation. Proceedings of the 2016 23rd International Conference on Pattern Recognition (ICPR), Cancun, Mexico.","DOI":"10.1109\/ICPR.2016.7900023"},{"key":"ref_27","unstructured":"Nogueira, F. (2022, June 06). Bayesian Optimization: Open Source Constrained Global Optimization Tool for Python. Available online: https:\/\/github.com\/fmfn\/BayesianOptimization."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Agrawal, T. (2020). Bayesian Optimization. Hyperparameter Optimization in Machine Learning, Apress.","DOI":"10.1007\/978-1-4842-6579-6"},{"key":"ref_29","unstructured":"Datta, L. (2020). A survey on activation functions and their relation with xavier and he normal initialization. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"e623","DOI":"10.7717\/peerj-cs.623","article-title":"The coefficient of determination R-squared is more informative than SMAPE, MAE, MAPE, MSE and RMSE in regression analysis evaluation","volume":"7","author":"Chicco","year":"2021","journal-title":"PeerJ Comput. Sci."},{"key":"ref_31","unstructured":"Stock, J.H., and Watson, M.W. (2005). Introduzione all\u2019econometria, Pearson Italia Spa."},{"key":"ref_32","unstructured":"Raschka, S. (2018). Model evaluation, model selection, and algorithm selection in machine learning. arXiv."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7311\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T00:40:08Z","timestamp":1760143208000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/19\/7311"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,27]]},"references-count":32,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2022,10]]}},"alternative-id":["s22197311"],"URL":"https:\/\/doi.org\/10.3390\/s22197311","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,27]]}}}